我不知道这是否可行，但我只是想以防万一。这是我的模型的(简化的(体系结构。
Layer (type) Output Shape Param #Connected to
==========================================
input_1 (InputLayer) [(None, 7, 7, 1024) 0
conv (Conv2D) (None, 7, 7, 10) 10240 input_1[0][0]
其中"1"中的10个滤波器中的每一个；conv"；是1x1x1024卷积滤波器(没有偏差，但与此特定问题无关(。我目前正在使用一个自定义正则化函数；conv"；以确保滤波器权重的(1x1(x1024x10矩阵具有良好的性质(基本上所有向量都是成对正交的(，并且到目前为止，一切都如预期的那样工作。现在，我还希望能够禁用这10个过滤器中的一些过滤器的训练。我知道如何做到这一点的唯一方法是独立实现10个过滤器，如下
Layer (type) Output Shape Param # Connected to
=========================================================
input_1 (InputLayer) [(None, 7, 7, 1024) 0
conv_1 (Conv2D) (None, 7, 7, 1) 1024 input_1[0][0]
conv_2 (Conv2D) (None, 7, 7, 1) 1024 input_1[0][0]
conv_3 (Conv2D) (None, 7, 7, 1) 1024 input_1[0][0]
...
conv_10 (Conv2D) (None, 7, 7, 1) 1024 input_1[0][0]
接着是连接层；可训练的"；参数设置为True/False。然而，现在我不知道如何实现我的正则化函数，它必须同时而不是独立地对所有层的权重conv_I进行计算。有什么技巧可以用来实现这样的功能吗？或者相反，有没有办法只冻结卷积层的部分权重？谢谢
解决方案
对于那些感兴趣的人，以下是我的问题的工作代码，遵循@LaplaseRicky提供的建议。
class SpecialRegularization(tf.keras.Model):
""" In order to avoid a warning message when saving the model,
I use the solution indicated here
https://github.com/tensorflow/tensorflow/issues/44541
and now inherit from tf.keras.Model instead of Layer
"""
def __init__(self,nfilters,**kwargs):
super().__init__(**kwargs)
self.inner_layers=[Conv2D(1,(1,1)) for _ in range(nfilters)]
def call(self, inputs):
outputs=[l(inputs) for l in self.inner_layers]
self.add_loss(self.define_your_regularization_here())
return tf.concat(outputs,-1)
def set_trainable_parts(self, trainables):
""" Set the trainable attribute independently on each filter """
for l,t in zip(self.inner_layers,trainables):
l.trainable = t
def define_your_regularization_here(self):
#reconstruct the original kernel
large_kernel=tf.concat([l.kernel for l in self.inner_layers],-1)
return tf.reduce_sum(large_kernel*large_kernel[:,:,:,::-1])
实现这一点的一种方法是拥有一个自定义keras层，该层包裹所有小的conv层，并负责计算正则化损失。
示例代码：
import tensorflow as tf
def _get_losses(model,x):
model(x)
return model.losses
def _get_grads(model,x):
with tf.GradientTape() as t:
model(x)
reg_loss=tf.math.add_n(model.losses)
return t.gradient(reg_loss,model.trainable_weights)
class SpecialRegularization(tf.keras.layers.Layer):
def __init__(self, **kwargs):
self.inner_layers=[tf.keras.layers.Conv2D(1,(1,1)) for i in range(10)]
super().__init__(**kwargs)
def call(self, inputs,training=None):
outputs=[l(inputs,training=training) for l in self.inner_layers]
self.add_loss(self.define_your_regularization_here())
return tf.concat(outputs,-1)
def define_your_regularization_here(self):
#reconstruct the original kernel
large_kernel=tf.concat([l.kernel for l in self.inner_layers],-1)
#just giving an example here
#you should define your own regularization using the entire kernel
return tf.reduce_sum(large_kernel*large_kernel[:,:,:,::-1])
tf.random.set_seed(123)
inputs = tf.keras.Input(shape=(7,7,1024))
outputs = SpecialRegularization()(inputs)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
#get_losses, get_grads are for demonstration purpose
get_losses=tf.function(_get_losses)
get_grads=tf.function(_get_grads)
data=tf.random.normal((64,7,7,1024))
print(get_losses(model,data))
print(get_grads(model,data)[0])
print(model.layers[1].inner_layers[-1].kernel*2)
model.summary()
'''
[<tf.Tensor: shape=(), dtype=float32, numpy=-0.20446025>]
tf.Tensor(
[[[[ 0.02072023]
[ 0.12973154]
[ 0.11631528]
...
[ 0.00804012]
[-0.07299817]
[ 0.06031524]]]], shape=(1, 1, 1024, 1), dtype=float32)
tf.Tensor(
[[[[ 0.02072023]
[ 0.12973154]
[ 0.11631528]
...
[ 0.00804012]
[-0.07299817]
[ 0.06031524]]]], shape=(1, 1, 1024, 1), dtype=float32)
Model: "model"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 7, 7, 1024)] 0
_________________________________________________________________
special_regularization (Spec (None, 7, 7, 10) 10250
=================================================================
Total params: 10,250
Trainable params: 10,250
Non-trainable params: 0
_________________________________________________________________
'''